© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130574
    Prev
    Next
    INDEX
    Explanations

    Medical/scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reck
    -0.27
    åľ¨ä¸ĢæĹģ
    -0.26
    ropa
    -0.26
    æĺ¯åIJ¦ä¼ļ
    -0.25
    atat
    -0.25
    ï¼ļ<
    -0.25
    propri
    -0.25
    hea
    -0.24
    ipa
    -0.24
     Downs
    -0.24
    POSITIVE LOGITS
    好
    0.29
    //
    0.28
    standen
    0.25
     i
    0.25
    ä»İåīį
    0.25
    .test
    0.24
    è¶Ĭ好
    0.24
    .search
    0.24
    gid
    0.24
    æĦĪ
    0.24
    Activations Density 3.951%

    No Known Activations